{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VACBQK6ICZO3Z37AW2XZJC4FJD","short_pith_number":"pith:VACBQK6I","canonical_record":{"source":{"id":"2204.06699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T01:53:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04bec0b02769d52e48013bcc3d13ab029604ff6429efd7cb8806264751504341","abstract_canon_sha256":"743719de8a15a2cc8ba1645930b933f9b1d8351f8ffeeeef1e76b5a337e9587a"},"schema_version":"1.0"},"canonical_sha256":"a804182bc8165dbcefe0b6af948b8548c847d9798cc8ccdf499374b514e2493e","source":{"kind":"arxiv","id":"2204.06699","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06699","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06699v1","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06699","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"VACBQK6ICZO3","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"VACBQK6ICZO3Z37A","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"VACBQK6I","created_at":"2026-07-05T04:14:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VACBQK6ICZO3Z37AW2XZJC4FJD","target":"record","payload":{"canonical_record":{"source":{"id":"2204.06699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T01:53:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04bec0b02769d52e48013bcc3d13ab029604ff6429efd7cb8806264751504341","abstract_canon_sha256":"743719de8a15a2cc8ba1645930b933f9b1d8351f8ffeeeef1e76b5a337e9587a"},"schema_version":"1.0"},"canonical_sha256":"a804182bc8165dbcefe0b6af948b8548c847d9798cc8ccdf499374b514e2493e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:14:44.971942Z","signature_b64":"Q090apKge+MIC4M05FdEG5C62oMOoUrp8P7gmlboZz3HsnBamenEQtjC/xIJ+4RDtZV/xgahe3CpcUUS6YI/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a804182bc8165dbcefe0b6af948b8548c847d9798cc8ccdf499374b514e2493e","last_reissued_at":"2026-07-05T04:14:44.971541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:14:44.971541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.06699","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+5ezlkOYPZ6vVFHaI0YfJxlJTo2ZWsXbt6N9Ee2Jo06SSchyKnsK8oVQDhXPbHj4IQ+8Quiui+kkEVo4nTg/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:33.953350Z"},"content_sha256":"892763259230d66ec307cb25c4c107c59a1a1b1f8c6a8546cf72d5c415e297c0","schema_version":"1.0","event_id":"sha256:892763259230d66ec307cb25c4c107c59a1a1b1f8c6a8546cf72d5c415e297c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VACBQK6ICZO3Z37AW2XZJC4FJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Nancy Y. Ip, Pascale Fung, Samuel Cahyawijaya, Tiezheng Yu, Tiffany T.W. Mak, Xiaopu Zhou, Zihan Liu","submitted_at":"2022-04-14T01:53:58Z","abstract_excerpt":"Self-supervised pre-training methods have brought remarkable breakthroughs in the understanding of text, image, and speech. Recent developments in genomics has also adopted these pre-training methods for genome understanding. However, they focus only on understanding haploid sequences, which hinders their applicability towards understanding genetic variations, also known as single nucleotide polymorphisms (SNPs), which is crucial for genome-wide association study. In this paper, we introduce SNP2Vec, a scalable self-supervised pre-training approach for understanding SNP. We apply SNP2Vec to pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06699","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.06699/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lhZtAIHVkBbRp4+Zl8OTirTXvvP1aQrKQV2YwUJT/261bkwvYMRkl9LOI8ybX2Ck2j1FZALcdtHiBsOxyuKaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:12:33.954508Z"},"content_sha256":"6dfe3df60e62b1b4461e0e685ba1ebe06b7f55b4c6740b9f90655a0cdc54cea7","schema_version":"1.0","event_id":"sha256:6dfe3df60e62b1b4461e0e685ba1ebe06b7f55b4c6740b9f90655a0cdc54cea7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VACBQK6ICZO3Z37AW2XZJC4FJD/bundle.json","state_url":"https://pith.science/pith/VACBQK6ICZO3Z37AW2XZJC4FJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VACBQK6ICZO3Z37AW2XZJC4FJD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T12:12:33Z","links":{"resolver":"https://pith.science/pith/VACBQK6ICZO3Z37AW2XZJC4FJD","bundle":"https://pith.science/pith/VACBQK6ICZO3Z37AW2XZJC4FJD/bundle.json","state":"https://pith.science/pith/VACBQK6ICZO3Z37AW2XZJC4FJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VACBQK6ICZO3Z37AW2XZJC4FJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VACBQK6ICZO3Z37AW2XZJC4FJD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"743719de8a15a2cc8ba1645930b933f9b1d8351f8ffeeeef1e76b5a337e9587a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T01:53:58Z","title_canon_sha256":"04bec0b02769d52e48013bcc3d13ab029604ff6429efd7cb8806264751504341"},"schema_version":"1.0","source":{"id":"2204.06699","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06699","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06699v1","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06699","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"VACBQK6ICZO3","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"VACBQK6ICZO3Z37A","created_at":"2026-07-05T04:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"VACBQK6I","created_at":"2026-07-05T04:14:44Z"}],"graph_snapshots":[{"event_id":"sha256:6dfe3df60e62b1b4461e0e685ba1ebe06b7f55b4c6740b9f90655a0cdc54cea7","target":"graph","created_at":"2026-07-05T04:14:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.06699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised pre-training methods have brought remarkable breakthroughs in the understanding of text, image, and speech. Recent developments in genomics has also adopted these pre-training methods for genome understanding. However, they focus only on understanding haploid sequences, which hinders their applicability towards understanding genetic variations, also known as single nucleotide polymorphisms (SNPs), which is crucial for genome-wide association study. In this paper, we introduce SNP2Vec, a scalable self-supervised pre-training approach for understanding SNP. We apply SNP2Vec to pe","authors_text":"Nancy Y. Ip, Pascale Fung, Samuel Cahyawijaya, Tiezheng Yu, Tiffany T.W. Mak, Xiaopu Zhou, Zihan Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T01:53:58Z","title":"SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06699","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:892763259230d66ec307cb25c4c107c59a1a1b1f8c6a8546cf72d5c415e297c0","target":"record","created_at":"2026-07-05T04:14:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"743719de8a15a2cc8ba1645930b933f9b1d8351f8ffeeeef1e76b5a337e9587a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-14T01:53:58Z","title_canon_sha256":"04bec0b02769d52e48013bcc3d13ab029604ff6429efd7cb8806264751504341"},"schema_version":"1.0","source":{"id":"2204.06699","kind":"arxiv","version":1}},"canonical_sha256":"a804182bc8165dbcefe0b6af948b8548c847d9798cc8ccdf499374b514e2493e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a804182bc8165dbcefe0b6af948b8548c847d9798cc8ccdf499374b514e2493e","first_computed_at":"2026-07-05T04:14:44.971541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:44.971541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q090apKge+MIC4M05FdEG5C62oMOoUrp8P7gmlboZz3HsnBamenEQtjC/xIJ+4RDtZV/xgahe3CpcUUS6YI/BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:44.971942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.06699","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:892763259230d66ec307cb25c4c107c59a1a1b1f8c6a8546cf72d5c415e297c0","sha256:6dfe3df60e62b1b4461e0e685ba1ebe06b7f55b4c6740b9f90655a0cdc54cea7"],"state_sha256":"5e4d118ad97ad115932818c5f6aec926a89d130bfede77a9c63766fb2e0bf030"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7oqE/KGtAvEHHv+1etl0gpq55DiDboMqSjCsOT6GMiBoyI0nZApCWYCgJfe6RZM9iScSY2tH5KGiucLSQaKAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:12:33.982506Z","bundle_sha256":"6722c0882bf5cdb2647883bc09f7cab0c3105e1fa0b993e7ccb6b3954761aec0"}}